Taking the guesswork out of artificial intelligence
Interpretable AI builds machine learning solutions that bridge the gap between interpretability and performance
You can't depend on an AI system you don't understand
Our interpretable models are fully-understandable by humans, ensuring the logic of the system can be inspected, audited and trusted.
Our interpretable algorithms are transparent and understandable
Model transparency allows us to leverage domain knowledge from all parts of the organization, leading not only to better models, but ensuring that the model actually solves the right problem and has buy-in from all relevant stakeholders.
Interpretable AI Algorithms
Interpretability and performance
Based on cutting-edge research published in the top academic journals, our technologies simultaneously deliver interpretability and state-of-the-art performance
-
Optimal Imputation
Unlock the full power of data with missing values or quality issues
-
Optimal Feature Selection
Automatic selection of optimal features from the noise
-
Optimal Decision Trees
As powerful as black-box artificial intelligence with the interpretability of a single decision tree
-
Interpretable Matrix Completion
Powerful recommender system that gives detailed explanations for each suggestion
-
Causal Inference and Policy Learning
Learning interpretable rules while accounting for biases from observational data
Extensive experience developing solutions with partners
We have applied our methods successfully with global partners that are industry leaders. We leverage our expertise in interpretable methods and combine it with the vast domain knowledge in your business.
Available for licensing
We provide familiar and flexible interfaces to our methods in Julia, Python and R
All licensing is free for academic users.
World-class expertise and leading research in interpretability
Each member of our team holds an advanced degree from MIT in machine learning and data analytics.